app.py

# %% app.ipynb 1
import gradio as gr
from fastai.vision.all import *

# %% app.ipynb 2
learn = load_learner('pets-model.pkl')
labels = learn.dls.vocab

# %% app.ipynb 3
def predict(img):
    img = PILImage.create(img)
    pred, pred_idx, probs = learn.predict(img)
    return {labels[i]: float(probs[i]) for i in range(len(labels))}

# %% app.ipynb 4
title = "Pet Breed Classifier"
description = "A pet breed classifier trained on the Oxford Pets dataset with fastai. Created as a demo for Gradio and HuggingFace Spaces."
article = "<p style='text-align: center'><a href='https://tmabraham.github.io/blog/gradio_hf_spaces_tutorial' target='_blank'>Blog post</a></p>"
#interpretation = 'default'
interpretation = 'shap'
enable_queue = True

# %% app.ipynb 5
image = gr.inputs.Image(shape=(224,224))
label = gr.outputs.Label(num_top_classes=3)
examples = ['british.jpg', 'newfoundland.jpg', 'shiba.jpg']

# %% app.ipynb 6
intf = gr.Interface(fn=predict, inputs=image, outputs=label, title=title,
             description=description, article=article, examples=examples, interpretation=interpretation, enable_queue=enable_queue)
intf.launch(inline=False)